Please use this identifier to cite or link to this item: http://dspace.mj.gov.br/handle/1/7644
Full metadata record
DC FieldValueLanguage
dc.contributor.authorSampaio, José Fabrizio Pereira.pt_BR
dc.date.accessioned2022-09-28T16:08:40Z-
dc.date.available2022-09-28T16:08:40Z-
dc.date.issued2018-07-
dc.identifier.urihttp://dspace.mj.gov.br/handle/1/7644-
dc.description.abstractAn audio recording must be authentic to be admitted as evidence in a criminal prose-cution so that the speech is saved with maximum fidelity and interpretation mistakes are prevented. AMR (adaptive multi-rate) encoder is a worldwide standard for speech compression and for GSM mobile network transmission, including 3G and 4G. In ad-dition, such encoder is an audio file format standard with extension AMR which uses the same compression algorithm. Due to its extensive usage in mobile networks and high availability in modern smartphones, AMR format has been found in audio au-thenticity cases for forger y searching. Such exams compound the multimedia forensics field which consists of, among other techniques, double compression detection, i. e., to determine if a given AMR file was decompressed and compressed again. AMR double compression detection is a complex engineering problem whose solution is still under-way. In general terms, if an AMR file is double compressed, it is not compatible with an original one and may have been doctored. The published works in literature about double compression detection are based on decoded waveform of the AMR files to extract features. In this paper, a new approach is proposed to AMR double compres-sion detection, which uses the encoded version to extract compressed-domain features based on linear prediction (LP) coefficients, in spite of processing decoded audio. By means of feature statistical analysis, it is possible to show that they can be used to achieve AMR double compression detection in an effective way. Therefore, compressed-do-main features can be considered a promising path to solve AMR double compression problem by artificial neural networks.pt_BR
dc.language.isoenpt_BR
dc.publisherAcademia Nacional de Políciapt_BR
dc.subjectPerícia (Processo Penal)pt_BR
dc.subjectTecnologia digitalpt_BR
dc.subjectCriminalísticapt_BR
dc.subjectInovação tecnológicapt_BR
dc.titleAMR Compressed-Domain analysis for multimedia forensics double compression detectionpt_BR
dc.title.alternativeAnálise forense de AMR Compressed-Domain para detecção de dupla compressão multimídiapt_BR
dc.title.alternativeAnálisis forense de AMR Compressed-Domain para detección de double compresión multimediapt_BR
dc.typeArtigo de revistapt_BR
dc.publisher.sourceRevista brasileira de ciências policiais, v. 9, n. 2, p. 43-70, jul./dez. 2018pt_BR
dc.description.otherInclui notas explicativas, bibliográficas e bibliografia.pt_BR
Appears in Collections:Revista Brasileira de Ciências Policiais - RBCP

Files in This Item:
File Description SizeFormat 
RBCP_N9_P43-70.pdf3.38 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.